© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109487
    Prev
    Next
    INDEX
    Explanations

    said [name]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -3.25
     и
    -1.41
    ;
    -1.36
     AND
    -1.21
    :
    -1.20
     for
    -1.14
     oraz
    -1.12
     -
    -1.11
     was
    -1.11
     is
    -1.10
    POSITIVE LOGITS
     who
    1.96
     adding
    1.73
     ajout
    1.56
     about
    1.55
     referring
    1.41
     during
    1.38
     when
    1.34
     of
    1.31
     after
    1.30
    Добавлено
    1.27
    Activations Density 0.023%

    No Known Activations